The Twin-System Approach as One Generic Solution for XAI: An Overview of ANN-CBR Twins for Explaining Deep Learning

The notion of twin systems is proposed to address the eXplainable AI (XAI) problem, where an uninterpretable black-box system is mapped to a white-box 'twin' that is more interpretable. In this short paper, we overview very recent work that advances a generic solution to the XAI problem, the so called twin system approach. The most popular twinning in the literature is that between an Artificial Neural Networks (ANN ) as a black box and Case Based Reasoning (CBR) system as a white-box, where the latter acts as an interpretable proxy for the former. We outline how recent work reviving this idea has applied it to deep learning methods. Furthermore, we detail the many fruitful directions in which this work may be taken; such as, determining the most (i) accurate feature-weighting methods to be used, (ii) appropriate deployments for explanatory cases, (iii) useful cases of explanatory value to users.

Plotting Markson's 'Mistress'

The post-modern novel 'Wittgenstein's Mistress' by David Markson (1988) presents the reader with a very challenging non linear narrative, that itself appears to one of the novel's themes. We present a distant reading of this work designed to complement a close reading of it by David Foster Wallace (1990). Using a combination of text analysis, entity recognition and networks, we plot repetitive structures in the novel's narrative relating them to its critical analysis.

Helping News Editors Write Better Headlines: A Recommender to Improve the Keyword Contents & Shareability of News Headlines

We present a software tool that employs state-of-the-art natural language processing (NLP) and machine learning techniques to help newspaper editors compose effective headlines for online publication. The system identifies the most salient keywords in a news article and ranks them based on both their overall popularity and their direct relevance to the article. The system also uses a supervised regression model to identify headlines that are likely to be widely shared on social media. The user interface is designed to simplify and speed the editor's decision process on the composition of the headline. As such, the tool provides an efficient way to combine the benefits of automated predictors of engagement and search-engine optimization (SEO) with human judgments of overall headline quality.

Cognitive residues of similarity

What are the cognitive after-effects of making a similarity judgement? What, cognitively, is left behind and what effect might these residues have on subsequent processing? In this paper, we probe for such after-effects using a visual search task, performed after a task in which pictures of real-world objects were compared. So, target objects were first presented in a comparison task (e.g., rate the similarity of this object to another) thus, presumably, modifying some of their features before asking people to visually search for the same object in complex scenes (with distractors and camouflaged backgrounds). As visual search is known to be influenced by the features of target objects, then any after-effects of the comparison task should be revealed in subsequent visual searches. Results showed that when people previously rated an object as being high on a scale (e.g., colour similarity or general similarity) then visual search is inhibited (slower RTs and more saccades in eye-tracking) relative to an object being rated as low in the same scale. There was also some evidence that different comparison tasks (e.g., compare on colour or compare on general similarity) have differential effects on visual search.

Surprise: Youve got some explaining to do

Why are some events more surprising than others? We propose that events that are more difficult to explain are those that are more surprising. The two experiments reported here test the impact of different event outcomes (Outcome-Type) and task demands (Task) on ratings of surprise for simple story scenarios. For the Outcome-Type variable, participants saw outcomes that were either known or less-known surprising outcomes for each scenario. For the Task variable, participants either answered comprehension questions or provided an explanation of the outcome. Outcome-Type reliably affected surprise judgments; known outcomes were rated as less surprising than less-known outcomes. Task also reliably affected surprise judgments; when people provided an explanation it lowered surprise judgments relative to simply answering comprehension questions. Both experiments thus provide evidence on this less-explored explanation aspect of surprise, specifically showing that ease of explanation is a key factor in determining the level of surprise experienced.

Innovation networks

This paper advances a framework for modeling the component interactions between cognitive and social aspects of scientific creativity and technological innovation. Specifically, it aims to characterize Innovation Networks; those networks that involve the interplay of people, ideas and organizations to create new, technologically feasible, commercially-realizable products, processes and organizational structures. The tri-partite framework captures networks of ideas (Concept Level), people (Individual Level) and social structures (Social-Organizational Level) and the interactions between these levels. At the concept level, new ideas are the nodes that are created and linked, kept open for further investigation or closed if solved by actors at the individual or organizational levels. At the individual level, the nodes are actors linked by shared worldviews (based on shared professional, educational, experiential backgrounds) who are the builders of the concept level. At the social-organizational level, the nodes are organizations linked by common efforts on a given project (e.g., a company-university collaboration) that by virtue of their intellectual property or rules of governance constrain the actions of individuals (at the Individual Level) or ideas (at the Concept Level). After describing this framework and its implications we paint a number of scenarios to flesh out how it can be applied.